arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.11626cs.LGcs.AIphysics.chem-phphysics.comp-phphysics.flu-dyn
收藏

ArGEnT:任意几何编码的Transformer用于运算符学习

ArGEnT: Arbitrary Geometry-encoded Transformer for Operator Learning

Pacific Northwest National Laboratory(太平洋西北国家实验室);Sandia National Laboratories(桑地亚国家实验室);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)

Wenqian Chen, Zhi-Feng Wei, Yucheng Fu, Michael Penwarden, Pratanu Roy, Panos Stinis

AI总结:

本文提出ArGEnT,一种基于Transformer的几何感知架构,用于在任意域上学习运算符。通过整合DeepONet,ArGEnT在流体动力学、固体力学和电化学系统中实现了更准确的预测和泛化性能。

摘要:

学习具有复杂、变化几何和参数物理设置的系统解算子是科学机器学习中的核心挑战。在许多查询领域如设计优化、控制和反问题中,替代建模必须在不同几何上泛化并允许在任意空间位置灵活评估。本文提出任意几何编码Transformer(ArGEnT),一种用于任意域运算符学习的几何感知注意力架构。ArGEnT利用Transformer注意力机制,直接从点云表示中编码几何信息,三种变体——自注意力、交叉注意力和混合注意力——采用不同的策略整合几何特征。通过将ArGEnT整合到DeepONet作为主网络,我们开发了一种替代建模框架,能够学习依赖几何和非几何输入的运算符映射,而无需显式将几何参数化为分支网络输入。在流体动力学、固体力学和电化学系统的基准问题中,我们证明了与标准DeepONet和其他现有几何感知替代模型相比,预测精度和泛化性能显著提高。特别是,交叉注意力Transformer变体能够实现准确的几何条件预测,减少对符号距离函数的依赖。通过结合灵活的几何编码与运算符学习能力,ArGEnT提供了一种可扩展的替代建模框架,用于优化、不确定性量化和复杂物理系统的数据驱动建模。

英文摘要:

Learning solution operators on arbitrary geometries remains a central challenge in scientific machine learning, especially for many-query simulation, physics-informed learning, and evolving geometries requiring accurate, geometry-aware predictions at arbitrary spatial locations. Existing operator-learning methods often rely on structured discretizations, explicit geometry parameterizations, or point-cloud formulations that couple geometric representation with solution-query sampling, limiting flexibility on irregular and non-parameterized domains. We propose the Arbitrary Geometry-encoded Transformer (ArGEnT), a geometry-conditioned attention framework that decouples geometry encoding from query-point evaluation. We develop three variants: self-attention, cross-attention, and hybrid-attention. ArGEnT can be used independently or integrated with neural operators to incorporate non-geometric physical inputs. In the cross-attention variant, geometry is represented by an independently sampled point cloud used to construct keys and values, while arbitrary solution-query points construct queries. This design enables mesh-independent field prediction, reduces sensitivity to query-point distribution, and allows compact geometric representations to condition large-scale solution evaluations. Across benchmarks in fluid dynamics, solid mechanics, and electrochemical systems, ArGEnT consistently improves accuracy and generalization over standard DeepONet, point-cloud-based operator learning, and geometry-aware transformer baselines. In several cases, it reduces prediction errors by more than an order of magnitude while requiring substantially lower training cost than transformer-based baselines. These results demonstrate that decoupled geometry-query attention provides an accurate, scalable, and flexible framework for operator learning on arbitrary geometries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑